Author

Lars L Schaaf

University of CambridgeORCID 0000-0002-1935-236XUnclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 3 Research Focus:protein design· 3 Assay:protein structure· 3 Approach:diffusion model· 2 Approach:benchmark study· 1 Research Focus:benchmarking· 1 Organism:human· 1 Assay:protein sequence· 1

Frequent Co-Authors

David A. BakeriD· 3 shared Kieran DidiiD· 3 shared Alex KangiD· 2 shared An‐Qi CheniD· 2 shared Asim K. BeraiD· 2 shared Brian CoventryiD· 2 shared Donald HilvertiD· 2 shared Donghyo KimiD· 2 shared

Activity by Year

2025-2026 · peak 2/yr

Co-Author Collaboration Network

10 top collaborators · 45 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

3 shared papersBiochemistry

David A. BakerORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

De novo design of cysteine proteases

Hojae Choi, Magnus S. Bauer, Brian Coventry, Preetham Venkatesh, An‐Qi Chen, Donghyo Kim, Asim K. Bera, Alex Kang, Hannah Nguyen, Shayan Sadre, Justin A. Decarreau, Emily Joyce, Bhanumathi Shankaran, Tuscan Rock Thompson, Gabriel Greenstein, , David A. Baker

This study designs de novo cysteine proteases with high activity and structural novelty, achieving 19% success rate and up to 3 x 10^7 rate enhancement over background reactions.

Nature · Oct 14, 2026Peer-reviewedBiochemistry

Computational design of metalloproteases

An‐Qi Chen, Kejia Wu, Hojae Choi, Preetham Venkatesh, Samuel J. Pellock, Nikita Hanikel, Hojeong Shin, Declan Evans, Kieran Didi, Lars L Schaaf, Cristina Díaz‐Perlas, Brian Coventry, Donghyo Kim, Seth M. Woodbury, Pengfei Ji, , David A. Baker

This paper designs de novo metalloproteases using RoseTTAFold Diffusion 2, achieving high activity and specificity for cleaving various substrates.

Nature · Oct 14, 2026Peer-reviewedBiochemistry

Accelerating Biomolecular Modeling with AtomWorks andRF3

Nathaniel Corley, Simon V. Mathis, Rohith Krishna, Magnus S. Bauer, Tuscan R. Thompson, Woody Ahern, Maxwell W. Kazman, Rafael I. Brent, Kieran Didi, Andrew Kubaney, Ryan McHugh, Arnav Nagle, Andrew Favor, Meghana Kshirsagar, Pascal Sturmfels, , Frank DiMaio

AtomWorks, a modular atom-level data framework, trains structure prediction and design models; the resulting RF3 improves chirality handling and performs between AF3 and Boltz.

bioRxiv · Aug 14, 2025 · PreprintBiochemistry✦ In-depth digest